metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: allsky-stars-detected
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9952153110047847
allsky-stars-detected
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0255
- Accuracy: 0.9952
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1339
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0436 | 1.0 | 148 | 0.0582 | 0.9809 |
| 0.0121 | 2.0 | 296 | 0.0405 | 0.9904 |
| 0.0112 | 3.0 | 444 | 0.0383 | 0.9856 |
| 0.01 | 4.0 | 592 | 0.0270 | 0.9952 |
| 0.0098 | 5.0 | 740 | 0.0255 | 0.9952 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.0+cpu
- Datasets 3.0.1
- Tokenizers 0.21.0